GPU VPS with a shared vGPU or a dedicated GPU
A virtual server with GPU power for AI, graphics and video. Choose a shared vGPU, a share of a physical GPU for lighter work, or a dedicated GPU that belongs to your server alone. Intel, NVIDIA or AMD, with full root access to install the drivers, frameworks and tools you need.
- Shared vGPU or a whole dedicated GPU
- Intel, NVIDIA or AMD GPUs
- Full root access for drivers and frameworks
- Docker containers with GPU access
Choose a plan that fits
Tell us what you need and our team will help you choose the right plan.
The GPU share your workload needs
A GPU VPS is a virtual server like our Linux and Windows VPS, with one difference: a GPU. With a shared vGPU, your server gets a share of a physical GPU, enough for smaller models, a private chat for your team, GPU-accelerated apps and remote desktops. With a dedicated GPU, a whole GPU belongs to your server, with all of its memory and compute, for larger models, more users and long jobs.
Both come with root access, the same client area and help from our team, and each plan names its GPU maker: Intel, NVIDIA or AMD.
- Shared vGPU: a share of a physical GPU for lighter work
- Dedicated GPU: a whole GPU with all of its memory
- Root access and the same tools on both
- Intel, NVIDIA or AMD, named in every plan
vps-01.example.com203.0.113.24 · Ubuntu 26.04
Running
A virtual server built around its GPU
Shared vGPU or dedicated GPU
Choose a share of a physical GPU for lighter work, or a whole GPU that belongs to your server alone.
Intel, NVIDIA or AMD
Each plan names its GPU maker, so you can match it to CUDA, ROCm or oneAPI software before you order.
Full root access
Install drivers, CUDA or ROCm, Python environments and your own services, with no panel in the way.
GPU in containers
Run Ollama, vLLM, ComfyUI or Jupyter images with GPU access through Docker or Podman.
Ready for AI tools
Serve open models with Ollama or vLLM, chat in Open WebUI and build image workflows in ComfyUI.
Your data on your server
Prompts, models, datasets and renders stay on a server you control instead of a shared SaaS account.
Room to grow
Move to a GPU VDS for nested virtualization, or to a GPU dedicated server when you need the whole machine.
One client area
Order, renew and manage the server and its invoices from the same client area as your other services.
Help from our team
Open a support ticket if the server, the GPU or the network needs attention, and follow every reply in one place.
What runs well on a GPU VPS
LLM inference for your apps and your team
Serve open models such as Llama, Qwen, Gemma or Mistral with Ollama, vLLM or llama.cpp behind an OpenAI-compatible API, and give your team a private chat with Open WebUI.
- OpenAI-compatible endpoints for your code
- Embeddings for search and RAG
- Prompts and documents stay on your server
$ ssh [email protected]
Welcome to Ubuntu 26.04 LTS (GNU/Linux x86_64)
root@vps:~# apt update && apt upgrade -y
0 upgraded, 0 newly installed, 0 to remove.
root@vps:~# ufw allow 443/tcp
Rule added
root@vps:~# systemctl is-active nginx
active
root@vps:~#
Image and video generation
Build ComfyUI workflows with your own checkpoints, LoRAs and custom nodes, queue them from the browser or the API, and let them run while you work on something else.
GPU rendering
Render scenes in Blender Cycles with CUDA or OptiX on NVIDIA, HIP on AMD or oneAPI on Intel GPUs, and let long jobs finish on the server instead of your workstation.
Video encoding and transcoding
FFmpeg can use the GPU’s hardware video engine: NVENC on NVIDIA, VA-API on AMD and Intel, and Quick Sync on Intel. Jellyfin and Immich use the same engines for media libraries.
Notebooks, fine-tuning and research
Run JupyterLab next to your data, try models with PyTorch on the GPU and fine-tune smaller models on your own datasets.
GPU-accelerated remote desktops
Give designers and engineers a remote workstation with GPU-accelerated graphics for CAD, 3D and video tools, reached over Remote Desktop or another remote display protocol.
Technical specifications
What every plan on this page shares. The GPU, vCPU, memory and storage differ by plan and are listed with each plan.
- GPU
- Intel, NVIDIA or AMD
- Each plan names its GPU
- GPU access
- Shared vGPU or dedicated GPU
- Each plan shows which one it includes
- Server type
- Virtual private server with full virtualization
- Need VMs inside? Choose a GPU VDS
- Access
- Root over SSH
- Remote Desktop on Windows systems
- Containers
- Docker and Podman with GPU access
- NVIDIA Container Toolkit, or /dev/kfd and /dev/dri for AMD and Intel
- GPU drivers
- Installed by you with root access
- NVIDIA driver and CUDA, AMD ROCm or Intel GPU drivers
- Operating systems
- Listed with each plan
- Pick one in the order form
- Locations
- Listed with each plan
- Pick one in the order form
- Support
- Support tickets from the client area
GPU VPS, GPU VDS or GPU dedicated server?
All three come with Intel, NVIDIA or AMD GPUs and root access. They differ in how much of the GPU and of the machine is yours.
| Feature |
This page GPU VPS
A virtual server with a GPU (Recommended)
|
GPU VDS
A larger virtual server with nested virtualization
|
GPU dedicated server
A whole physical server with its GPUs
|
|---|---|---|---|
| What you get | A virtual server with a GPU | A larger virtual server with a GPU and nested virtualization | A whole physical server with its GPUs |
| GPU | Shared vGPU or dedicated GPU | Shared vGPU or dedicated GPU | Every GPU in the machine |
| GPU makers | Intel, NVIDIA or AMD | Intel, NVIDIA or AMD | Intel, NVIDIA or AMD |
| Your own VMs insideNested virtualization passes the processor’s virtualization extensions to your server, so it can run virtual machines and Android emulators of its own. | Not included | Included | Yes, with your own hypervisor |
| Hardware used only by youA VPS or VDS is a virtual machine on a physical host that also runs other customers' virtual machines. | Not included | Not included | Included |
| Root access | Included | Included | Included |
| Best for | Inference, image generation, notebooks and remote desktops | Android emulators, GPU labs with VMs and larger AI stacks | Training, large models for many users and long render queues |
| Price level | Lowest | Middle | Highest |
-
This page
GPU VPS (Recommended)
A virtual server with a GPU
- What you get
- A virtual server with a GPU
- GPU
- Shared vGPU or dedicated GPU
- GPU makers
- Intel, NVIDIA or AMD
- Your own VMs insideNested virtualization passes the processor’s virtualization extensions to your server, so it can run virtual machines and Android emulators of its own.
- Not included
- Hardware used only by youA VPS or VDS is a virtual machine on a physical host that also runs other customers' virtual machines.
- Not included
- Root access
- Included
- Best for
- Inference, image generation, notebooks and remote desktops
- Price level
- Lowest
-
GPU VDS
A larger virtual server with nested virtualization
- What you get
- A larger virtual server with a GPU and nested virtualization
- GPU
- Shared vGPU or dedicated GPU
- GPU makers
- Intel, NVIDIA or AMD
- Your own VMs insideNested virtualization passes the processor’s virtualization extensions to your server, so it can run virtual machines and Android emulators of its own.
- Included
- Hardware used only by youA VPS or VDS is a virtual machine on a physical host that also runs other customers' virtual machines.
- Not included
- Root access
- Included
- Best for
- Android emulators, GPU labs with VMs and larger AI stacks
- Price level
- Middle
-
GPU dedicated server
A whole physical server with its GPUs
- What you get
- A whole physical server with its GPUs
- GPU
- Every GPU in the machine
- GPU makers
- Intel, NVIDIA or AMD
- Your own VMs insideNested virtualization passes the processor’s virtualization extensions to your server, so it can run virtual machines and Android emulators of its own.
- Yes, with your own hypervisor
- Hardware used only by youA VPS or VDS is a virtual machine on a physical host that also runs other customers' virtual machines.
- Included
- Root access
- Included
- Best for
- Training, large models for many users and long render queues
- Price level
- Highest
A comparison of the three GPU lines, not of single plans: each page lists its plans with the GPU, resources and price.
Set up your GPU VPS
Step-by-step guides for GPU drivers, model servers and AI tools, written for current Ubuntu and Debian releases.
-
How to install Ollama on Ubuntu or Debian and run local LLMs
Install Ollama as a systemd service, pull and run open models on CPU or GPU, test the REST API, move model storage and reach the API securely without exposing port 11434.
30 min Beginner -
How to run Open WebUI with Ollama using Docker Compose and HTTPS
Deploy Open WebUI with Docker Compose next to Ollama, connect them without opening port 11434, create the admin account privately, publish it over HTTPS with Caddy and keep it backed up and updated.
35 min Intermediate -
How to install ComfyUI on an NVIDIA GPU server securely
Set up ComfyUI from the official repository on a GPU server, run it under its own user with systemd, keep it off the public internet, add HTTPS with basic authentication, and manage models, custom nodes, backups and updates.
45 min Intermediate -
How to install vLLM on an NVIDIA GPU server with Docker
Prepare an NVIDIA GPU server, run vllm/vllm-openai with Docker Compose on 127.0.0.1, secure it with an API key and a Caddy proxy that only exposes /v1, tune memory and multi-GPU settings, or install it with uv and systemd.
45 min Advanced -
How to install JupyterLab on a Linux server with systemd and HTTPS
Set up single-user JupyterLab for a dedicated Linux user: virtual environment, hashed password, a systemd service bound to 127.0.0.1, SSH tunnel or Caddy access, GPU support, backups and updates.
30 min Intermediate -
How to run llama.cpp server as an OpenAI-compatible API
Compile llama.cpp, test llama-server with a GGUF model from Hugging Face, run it as a hardened systemd service on 127.0.0.1 with an API key, and publish the OpenAI-compatible API over HTTPS.
40 min Intermediate
What you get with HyperDC
One account for everything
Hosting, servers, domains and invoices are managed from the same client area.
Invoices in one place
Every invoice is listed in the client area, where you can also pay it online.
Support from the client area
Open a support ticket whenever you need help and follow every reply in one place.
From order to online
-
Choose a service
Pick the product, location and billing cycle that fit your project.
-
Complete your order
Review your cart and pay with one of the available payment methods.
-
Receive your details
We email your login details as soon as the service is ready.
-
Get help when you need it
Open a support ticket from the client area and follow every reply.
One provider for hosting, servers and domains
Hosting and servers since ٢٠١٣, with ٢٦٧k+ websites hosted on our services.
One client area for every service
Order, manage and pay for hosting, servers and domains from the same account.
Linux VPSActiveHelp from our team
Open a support ticket from the client area and follow every reply.
Choose your location
Pick the data center when you order. Each service page lists where it runs.
All data centersRoom to grow
Move between hosting, VPS, VDS and dedicated servers as your project grows.
Compare serversMoving from another provider?
Tell us what you run today and where it is hosted. We will reply with the steps to move it to your new HyperDC service.
- Tell us what you run today and where it is hosted
- Get the steps to move it to your new HyperDC service
- Switch over when everything is ready
Services that work well together
Policies that apply
Frequently asked questions
What is a GPU VPS?
A GPU VPS is a virtual private server with GPU acceleration. Next to its vCPU, memory and storage it has a GPU: either a shared vGPU, a share of a physical GPU, or a dedicated GPU that belongs to your server alone. You get full root access and install the drivers and software you need, as on any of our virtual servers.
What is the difference between a shared vGPU and a dedicated GPU?
A shared vGPU gives your server a share of a physical GPU, which suits smaller models, inference for a few users, GPU-accelerated apps and remote desktops. A dedicated GPU assigns a whole GPU to your server, with all of its memory and compute, for larger models, many users, fine-tuning and long rendering jobs. Each plan on this page shows which of the two it includes.
Which GPUs do you offer?
Intel, NVIDIA and AMD GPUs. Each plan names its GPU, so you can check it against the requirements of your software, for example CUDA for NVIDIA, ROCm for AMD or oneAPI for Intel, before you order.
Which operating systems can I install?
The systems each plan offers are listed on this page and in the order form. Choose a release your GPU software supports: NVIDIA’s CUDA and driver guides cover current Ubuntu LTS and Debian releases, and AMD’s ROCm documentation lists the Linux distributions it supports.
How do I install the GPU driver?
You install it yourself with root access, following the GPU maker’s documentation: NVIDIA’s driver and CUDA toolkit, AMD ROCm or Intel’s GPU drivers. Our guides for Ollama, vLLM and ComfyUI walk through the NVIDIA setup step by step, and our team helps through a support ticket if you are unsure which package fits your plan.
Can I use the GPU inside Docker?
Yes. With an NVIDIA GPU, install the NVIDIA Container Toolkit and start containers with --gpus all or the matching Compose setting; AMD and Intel GPUs are passed to containers as devices such as /dev/kfd and /dev/dri. Images for Ollama, vLLM, ComfyUI and Open WebUI then use the GPU.
GPU VPS or GPU VDS: which one do I need?
Both are virtual servers with a shared vGPU or a dedicated GPU. A GPU VDS adds nested virtualization, so you can run your own virtual machines, Android emulators or a hypervisor inside it. Choose a GPU VPS when your workload runs directly on the server, and a GPU VDS when you need virtual machines inside it.
When should I choose a GPU dedicated server instead?
When you need the whole physical machine: every GPU in it, all of its processor cores and memory, and no other customer on the hardware. That suits training, large models served to many users, long rendering queues and your own hypervisor with GPU passthrough.
Can I start without a GPU?
Yes. Small quantized models run on a Linux VPS with enough memory through Ollama or llama.cpp, which is a good way to test your setup. Move to a GPU VPS when you need faster answers, larger models or image generation.
How do I connect to my GPU VPS?
On Linux you sign in as root over SSH; on a Windows system you connect with Remote Desktop. We email the login details when the server is ready, and you manage the service, invoices and support tickets from the client area.
Which billing cycles can I choose?
Every plan lists the billing cycles it is offered with. Switch the cycle above the plans to compare prices; longer cycles show the saving against monthly billing when there is one.
How do I pay?
Choose one of the payment methods offered at checkout. Every invoice also stays available in the client area, where you can pay it online.
Where do I manage my service after ordering?
Your service appears in the client area as soon as it is set up. From there you can manage it, pay invoices and open support tickets.
Questions before you order?
Send us a message and our team will help you choose the right service.